linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: David Woodhouse <dwmw2@infradead.org>
To: Mike Rapoport <rppt@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	"Sauerwein, David" <dssauerw@amazon.de>,
	Anshuman Khandual <anshuman.khandual@arm.com>,
	Ard Biesheuvel <ardb@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	David Hildenbrand <david@redhat.com>,
	Marc Zyngier <maz@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Mike Rapoport <rppt@linux.ibm.com>, Will Deacon <will@kernel.org>,
	kvmarm@lists.cs.columbia.edu,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Ruihan Li <lrh2000@pku.edu.cn>
Subject: [PATCH v3 3/7] mm: Implement for_each_valid_pfn() for CONFIG_SPARSEMEM
Date: Wed, 23 Apr 2025 08:52:45 +0100	[thread overview]
Message-ID: <20250423081828.608422-4-dwmw2@infradead.org> (raw)
In-Reply-To: <20250423081828.608422-1-dwmw2@infradead.org>

From: David Woodhouse <dwmw@amazon.co.uk>

Implement for_each_valid_pfn() based on two helper functions.

The first_valid_pfn() function largely mirrors pfn_valid(), calling into
a pfn_section_first_valid() helper which is trivial for the !VMEMMAP case,
and in the VMEMMAP case will skip to the next subsection as needed.

Since next_valid_pfn() knows that its argument *is* a valid PFN, it
doesn't need to do any checking at all while iterating over the low bits
within a (sub)section mask; the whole (sub)section is either present or
not.

Note that the VMEMMAP version of pfn_section_first_valid() may return a
value *higher* than end_pfn when skipping to the next subsection, and
first_valid_pfn() happily returns that higher value. This is fine.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Previous-revision-reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/asm-generic/memory_model.h | 26 ++++++++--
 include/linux/mmzone.h             | 78 ++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+), 5 deletions(-)

diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 74d0077cc5fa..044536da3390 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -31,12 +31,28 @@ static inline int pfn_valid(unsigned long pfn)
 }
 #define pfn_valid pfn_valid
 
+static inline bool first_valid_pfn(unsigned long *pfn)
+{
+	/* avoid <linux/mm.h> include hell */
+	extern unsigned long max_mapnr;
+	unsigned long pfn_offset = ARCH_PFN_OFFSET;
+
+	if (*pfn < pfn_offset) {
+		*pfn = pfn_offset;
+		return true;
+	}
+
+	if ((*pfn - pfn_offset) < max_mapnr)
+		return true;
+
+	return false;
+}
+
 #ifndef for_each_valid_pfn
-#define for_each_valid_pfn(pfn, start_pfn, end_pfn)			 \
-	for ((pfn) = max_t(unsigned long, (start_pfn), ARCH_PFN_OFFSET); \
-	     (pfn) < min_t(unsigned long, (end_pfn),			 \
-			   ARCH_PFN_OFFSET + max_mapnr);		 \
-	     (pfn)++)
+#define for_each_valid_pfn(pfn, start_pfn, end_pfn)			       \
+	for (pfn = max_t(unsigned long, start_pfn, ARCH_PFN_OFFSET);	\
+	     pfn < min_t(unsigned long, end_pfn, ARCH_PFN_OFFSET + max_mapnr); \
+			 pfn++)
 #endif /* for_each_valid_pfn */
 #endif /* valid_pfn */
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 230a29c2ed1a..dab1d31477d7 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -2075,11 +2075,37 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 
 	return usage ? test_bit(idx, usage->subsection_map) : 0;
 }
+
+static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn)
+{
+	struct mem_section_usage *usage = READ_ONCE(ms->usage);
+	int idx = subsection_map_index(*pfn);
+	unsigned long bit;
+
+	if (!usage)
+		return false;
+
+	if (test_bit(idx, usage->subsection_map))
+		return true;
+
+	/* Find the next subsection that exists */
+	bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx);
+	if (bit == SUBSECTIONS_PER_SECTION)
+		return false;
+
+	*pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION);
+	return true;
+}
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	return 1;
 }
+
+static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn)
+{
+	return true;
+}
 #endif
 
 void sparse_init_early_section(int nid, struct page *map, unsigned long pnum,
@@ -2128,6 +2154,58 @@ static inline int pfn_valid(unsigned long pfn)
 
 	return ret;
 }
+
+/* Returns end_pfn or higher if no valid PFN remaining in range */
+static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn)
+{
+	unsigned long nr = pfn_to_section_nr(pfn);
+
+	rcu_read_lock_sched();
+
+	while (nr <= __highest_present_section_nr && pfn < end_pfn) {
+		struct mem_section *ms = __pfn_to_section(pfn);
+
+		if (valid_section(ms) &&
+		    (early_section(ms) || pfn_section_first_valid(ms, &pfn))) {
+			rcu_read_unlock_sched();
+			return pfn;
+		}
+
+		/* Nothing left in this section? Skip to next section */
+		nr++;
+		pfn = section_nr_to_pfn(nr);
+	}
+
+	rcu_read_unlock_sched();
+	return end_pfn;
+}
+
+static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn)
+{
+	pfn++;
+
+	if (pfn >= end_pfn)
+		return end_pfn;
+
+	/*
+	 * Either every PFN within the section (or subsection for VMEMMAP) is
+	 * valid, or none of them are. So there's no point repeating the check
+	 * for every PFN; only call first_valid_pfn() the first time, and when
+	 * crossing a (sub)section boundary (i.e. !(pfn & ~PFN_VALID_MASK)).
+	 */
+	if (pfn & (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ?
+		   PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK))
+		return pfn;
+
+	return first_valid_pfn(pfn, end_pfn);
+}
+
+
+#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn)			\
+	for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn));	\
+	     (_pfn) < (_end_pfn);					\
+	     (_pfn) = next_valid_pfn((_pfn), (_end_pfn)))
+
 #endif
 
 static inline int pfn_in_present_section(unsigned long pfn)
-- 
2.49.0



  parent reply	other threads:[~2025-04-23  8:18 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-23  7:52 [PATCH v3 0/7] mm: Introduce for_each_valid_pfn() David Woodhouse
2025-04-23  7:52 ` [PATCH v3 1/7] mm: Introduce for_each_valid_pfn() and use it from reserve_bootmem_region() David Woodhouse
2025-04-23  7:52 ` [PATCH v3 2/7] mm: Implement for_each_valid_pfn() for CONFIG_FLATMEM David Woodhouse
2025-04-23  7:52 ` David Woodhouse [this message]
2025-04-23 11:11   ` [PATCH v3 3/7] mm: Implement for_each_valid_pfn() for CONFIG_SPARSEMEM Mike Rapoport
2025-04-23 12:05     ` David Woodhouse
2025-04-23  7:52 ` [PATCH v3 4/7] mm, PM: Use for_each_valid_pfn() in kernel/power/snapshot.c David Woodhouse
2025-04-23 11:12   ` Mike Rapoport
2025-04-23  7:52 ` [PATCH v3 5/7] mm, x86: Use for_each_valid_pfn() from __ioremap_check_ram() David Woodhouse
2025-04-23 11:13   ` Mike Rapoport
2025-04-23  7:52 ` [PATCH v3 6/7] mm: Use for_each_valid_pfn() in memory_hotplug David Woodhouse
2025-04-23 11:13   ` Mike Rapoport
2025-04-23  7:52 ` [PATCH v3 7/7] mm/mm_init: Use for_each_valid_pfn() in init_unavailable_range() David Woodhouse
2025-04-23  9:35   ` Ruihan Li
2025-04-23 11:14   ` Mike Rapoport

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250423081828.608422-4-dwmw2@infradead.org \
    --to=dwmw2@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=anshuman.khandual@arm.com \
    --cc=ardb@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=david@redhat.com \
    --cc=dssauerw@amazon.de \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lrh2000@pku.edu.cn \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=rppt@kernel.org \
    --cc=rppt@linux.ibm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox